A PyTorch implementation of "MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer"

end-to-end DeepLab V3+ semantic segmentation pipeline, implemented with tf.keras

CoreNet: A library for training deep neural networks

Research repository for the IS-WiN laboratory at Clemson University. Conducted research includes; inference, classification, and GPU-[CUDA] CNN accelerations.

Universal DDPM for Data Synthesis

这是一个deeplabv3-plus-pytorch的源码，可以用于训练自己的模型。

An Object Detection Model for Remote Sensing Images Based on Attention Mechanism and Improved Downsampling Strategy.

Implementation of a Deep Neural Architecture to perform real-time semantic segmentation of forest fires in aerial imagery captured by drones.

[CVPR'24] UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio, Video, Point Cloud, Time-Series and Image Recognition

TransDeepLab: Convolution-Free Transformer-based DeepLab v3+ for Medical Image Segmentation

This is an official implementation of "Polarized Self-Attention: Towards High-quality Pixel-wise Regression"

DenseASPP for Semantic Segmentation in Street Scenes

Pytorch implementation of U-Net, R2U-Net, Attention U-Net, and Attention R2U-Net.

Using MobileNet as the backbone of UNet

Cell localization and counting: 1) Exponential Distance Transform Maps for Cell Localization; 2) Multi-scale Hypergraph-based Feature Alignment Network for Cell Localization; 3) Lite-UNet: A lightw…

Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.

UFS-Net: Unified Flame and Smoke detection method for early detection of fire in video-surveillance applications using CNNs

The open source code of SA-UNet: Spatial Attention U-Net for Retinal Vessel Segmentation.

UNetFormer: A UNet-like transformer for efficient semantic segmentation of remote sensing urban scene imagery, ISPRS. Also, including other vision transformers and CNNs for satellite, aerial image …

Mamba SSM architecture

[IEEE GRSL] The official implementation of UNetMamba: An Efficient UNet-Like Mamba for Semantic Segmentation of High-Resolution Remote Sensing Images on PyTorch

这是一个unet-pytorch的源码，可以训练自己的模型

Wining solution and its improvement for MICCAI 2017 Robotic Instrument Segmentation Sub-Challenge

🎨 Semantic segmentation models, datasets and losses implemented in PyTorch.

Understanding Convolution for Semantic Segmentation

2024_CAGEO_FPS-U2Net: Combining U2Net and multi-level aggregation architecture for fire point segmentation in remote sensing images

PyTorch implementation of the U-Net for image semantic segmentation with high quality images

[ECCV2024 - Oral] Adaptive Parametric Activation

Efficient Activation Function Optimization through Surrogate Modeling